Get the signals worth reading in your inbox

Email address

By subscribing, you agree to our privacy policy.

About Copyright PrivacyComplaints

Accelerate agentic AI with NVIDIA Nemotron models on Amazon… · Nvdium

←Back to feed

Home/Artificial intelligence/Article

Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKS

AAlex Iankoulski·AWS Machine Learning BlogPublished Oct 30, 2026, 12:34 AM· 7 min read

What happened

NVIDIA Nemotron 3.5 Super VL is a 120B-parameter mixture-of-experts model that pairs reasoning and tool use with multimodal understanding.

This post explores its architecture and use cases, then shows how to deploy it on Amazon EKS, EKS Auto Mode, and Amazon SageMaker HyperPod EKS with NVIDIA Dynamo and vLLM.

Was this useful?

Read original↗

Share this article

Go deeper

Gemini 4 Carbon: Our next frontier modelGoogle DeepMind Blog
AWS named a Leader in the 2026 Gartner Magic Quadrant for Contact Center as a ServiceAWS Machine Learning Blog
The sleep framework: A new way for LLMs to retain knowledge in continual learningGoogle Research Blog
Announcing SOCI-indexed images for faster SageMaker AI jobsAWS Machine Learning Blog
Fix evaluation bias to unlock better models on Amazon BedrockAWS Machine Learning Blog
Exowatt beats frontier models on accuracy with SageMaker serverless model customizationAWS Machine Learning Blog